source: branches/3076_IA_evaluators_analyzers/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator.cs @ 17794

#region License Information

/* HeuristicLab
 * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
 *
 * This file is part of HeuristicLab.
 *
 * HeuristicLab is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * HeuristicLab is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
 */

#endregion

using System;
using System.Collections.Generic;
using System.Linq;
using HEAL.Attic;
using HeuristicLab.Common;
using HeuristicLab.Core;
using HeuristicLab.Data;
using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
using HeuristicLab.Parameters;

namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression.MultiObjective {
  [Item("Multi Soft Constraints Evaluator",
    "Calculates the Person R² and the constraints violations of a symbolic regression solution.")]
  [StorableType("8E9D76B7-ED9C-43E7-9898-01FBD3633880")]
  public class
    SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator : SymbolicRegressionMultiObjectiveEvaluator
  {
    public const string DimensionsParameterName = "Dimensions";
    private const string BoundsEstimatorParameterName = "Bounds estimator";

    public IFixedValueParameter<IntValue> DimensionsParameter =>
      (IFixedValueParameter<IntValue>) Parameters[DimensionsParameterName];

    public IValueParameter<IBoundsEstimator> BoundsEstimatorParameter =>
      (IValueParameter<IBoundsEstimator>) Parameters[BoundsEstimatorParameterName];

    public IBoundsEstimator BoundsEstimator {
      get => BoundsEstimatorParameter.Value;
      set => BoundsEstimatorParameter.Value = value;
    }

    #region Constructors

    public SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator() {
      Parameters.Add(new FixedValueParameter<IntValue>(DimensionsParameterName, new IntValue(2)));
      Parameters.Add(new ValueParameter<IBoundsEstimator>(BoundsEstimatorParameterName, new IABoundsEstimator()));
    }

    [StorableConstructor]
    protected SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator(StorableConstructorFlag _) : base(_) { }

    protected SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator(
      SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator original, Cloner cloner) : base(original, cloner) { }

    #endregion

    [StorableHook(HookType.AfterDeserialization)]
    private void AfterDeserialization() {
      if (!Parameters.ContainsKey(DimensionsParameterName))
        Parameters.Add(new FixedValueParameter<IntValue>(DimensionsParameterName, new IntValue(2)));

      if (!Parameters.ContainsKey(BoundsEstimatorParameterName))
        Parameters.Add(new ValueParameter<IBoundsEstimator>(BoundsEstimatorParameterName, new IABoundsEstimator()));
    }

    public override IDeepCloneable Clone(Cloner cloner) {
      return new SymbolicRegressionMultiObjectiveMultiSoftConstraintEvaluator(this, cloner);
    }


    public override IOperation InstrumentedApply() {
      var rows = GenerateRowsToEvaluate();
      var solution = SymbolicExpressionTreeParameter.ActualValue;
      var problemData = ProblemDataParameter.ActualValue;
      var interpreter = SymbolicDataAnalysisTreeInterpreterParameter.ActualValue;
      var estimationLimits = EstimationLimitsParameter.ActualValue;
      var applyLinearScaling = ApplyLinearScalingParameter.ActualValue.Value;

      if (UseConstantOptimization) {
        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows,
          false,
          ConstantOptimizationIterations,
          ConstantOptimizationUpdateVariableWeights,
          estimationLimits.Lower,
          estimationLimits.Upper);
      } else {
        if (applyLinearScaling) {
          //Check for interval arithmetic grammar
          //remove scaling nodes for linear scaling evaluation
          var rootNode = new ProgramRootSymbol().CreateTreeNode();
          var startNode = new StartSymbol().CreateTreeNode();
          SymbolicExpressionTree newTree = null;
          foreach (var node in solution.IterateNodesPrefix())
            if (node.Symbol.Name == "Scaling") {
              for (var i = 0; i < node.SubtreeCount; ++i) startNode.AddSubtree(node.GetSubtree(i));
              rootNode.AddSubtree(startNode);
              newTree = new SymbolicExpressionTree(rootNode);
              break;
            }

          //calculate alpha and beta for scaling
          var estimatedValues = interpreter.GetSymbolicExpressionTreeValues(newTree, problemData.Dataset, rows);
          var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
          OnlineLinearScalingParameterCalculator.Calculate(estimatedValues, targetValues, out var alpha, out var beta,
            out var errorState);
          //Set alpha and beta to the scaling nodes from ia grammar
          foreach (var node in solution.IterateNodesPrefix())
            if (node.Symbol.Name == "Offset") {
              node.RemoveSubtree(1);
              var alphaNode = new ConstantTreeNode(new Constant()) {Value = alpha};
              node.AddSubtree(alphaNode);
            } else if (node.Symbol.Name == "Scaling") {
              node.RemoveSubtree(1);
              var betaNode = new ConstantTreeNode(new Constant()) {Value = beta};
              node.AddSubtree(betaNode);
            }
        }
      }

      var qualities = Calculate(interpreter, solution, estimationLimits.Lower, estimationLimits.Upper, problemData,
        rows, BoundsEstimator);
      QualitiesParameter.ActualValue = new DoubleArray(qualities);
      return base.InstrumentedApply();
    }

    public override double[] Evaluate(
      IExecutionContext context, ISymbolicExpressionTree tree,
      IRegressionProblemData problemData,
      IEnumerable<int> rows) {
      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
      EstimationLimitsParameter.ExecutionContext = context;
      ApplyLinearScalingParameter.ExecutionContext = context;

      var quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree,
        EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper,
        problemData, rows, BoundsEstimator);

      SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
      EstimationLimitsParameter.ExecutionContext = null;
      ApplyLinearScalingParameter.ExecutionContext = null;

      return quality;
    }


    public static double[] Calculate(
      ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,
      ISymbolicExpressionTree solution, double lowerEstimationLimit,
      double upperEstimationLimit,
      IRegressionProblemData problemData, IEnumerable<int> rows, IBoundsEstimator estimator) {
      OnlineCalculatorError errorState;
      var estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
      var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
      var constraints = problemData.IntervalConstraints.Constraints.Where(c => c.Enabled);
      var intervalCollection = problemData.VariableRanges;

      double nmse;

      var boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
      nmse = OnlineNormalizedMeanSquaredErrorCalculator.Calculate(targetValues, boundedEstimatedValues, out errorState);
      if (errorState != OnlineCalculatorError.None) nmse = 1.0;

      if (nmse > 1)
        nmse = 1.0;


      var objectives = new List<double> {nmse};
      ////var intervalInterpreter = new IntervalInterpreter() {UseIntervalSplitting = splitting};

      //var constraintObjectives = new List<double>();
      //foreach (var c in constraints) {
      //  var penalty = ConstraintExceeded(c, intervalInterpreter, variableRanges,
      //    solution);
      //  var maxP = 0.1;

      //  if (double.IsNaN(penalty) || double.IsInfinity(penalty) || penalty > maxP)
      //    penalty = maxP;

      //  constraintObjectives.Add(penalty);
      //}

      //objectives.AddRange(constraintObjectives);

      //return objectives.ToArray();

      var results = IntervalUtil.IntervalConstraintsViolation(constraints, estimator, intervalCollection, solution);
      foreach (var result in results) {
        if (double.IsNaN(result) || double.IsInfinity(result)) {
          objectives.Add(double.MaxValue);
        } else {
          objectives.Add(result);
        }
      }
      
      return objectives.ToArray();
    }

    /*
     * First objective is to maximize the Pearson R² value
     * All following objectives have to be minimized ==> Constraints
     */

    public override IEnumerable<bool> Maximization {
      get {
        var objectives = new List<bool> {false}; //First NMSE ==> min
        objectives.AddRange(Enumerable.Repeat(false, DimensionsParameter.Value.Value)); //Constraints ==> min

        return objectives;
      }
    }
  }
}